Publications

Dynamic Layer Normalization for Adaptive Neural Acoustic Modeling in Speech Recognition

Taesup Kim

Inchul Song

Yoshua Bengio

Layer normalization is a recently introduced technique for normalizing the activities of neurons in deep neural networks to improve the trai… (voir plus)ning speed and stability. In this paper, we introduce a new layer normalization technique called Dynamic Layer Normalization (DLN) for adaptive neural acoustic modeling in speech recognition. By dynamically generating the scaling and shifting parameters in layer normalization, DLN adapts neural acoustic models to the acoustic variability arising from various factors such as speakers, channel noises, and environments. Unlike other adaptive acoustic models, our proposed approach does not require additional adaptation data or speaker information such as i-vectors. Moreover, the model size is fixed as it dynamically generates adaptation parameters. We apply our proposed DLN to deep bidirectional LSTM acoustic models and evaluate them on two benchmark datasets for large vocabulary ASR experiments: WSJ and TED-LIUM release 2. The experimental results show that our DLN improves neural acoustic models in terms of transcription accuracy by dynamically adapting to various speakers and environments.

2017-08-19

Interspeech 2017 (publié)

Improving Speech Recognition by Revising Gated Recurrent Units

Mirco Ravanaelli

Philemon Brakel

Maurizio Omologo

Yoshua Bengio

Speech recognition is largely taking advantage of deep learning, showing that substantial benefits can be obtained by modern Recurrent Neura… (voir plus)l Networks (RNNs). The most popular RNNs are Long Short-Term Memory (LSTMs), which typically reach state-of-the-art performance in many tasks thanks to their ability to learn long-term dependencies and robustness to vanishing gradients. Nevertheless, LSTMs have a rather complex design with three multiplicative gates, that might impair their efficient implementation. An attempt to simplify LSTMs has recently led to Gated Recurrent Units (GRUs), which are based on just two multiplicative gates. This paper builds on these efforts by further revising GRUs and proposing a simplified architecture potentially more suitable for speech recognition. The contribution of this work is two-fold. First, we suggest to remove the reset gate in the GRU design, resulting in a more efficient single-gate architecture. Second, we propose to replace tanh with ReLU activations in the state update equations. Results show that, in our implementation, the revised architecture reduces the per-epoch training time with more than 30% and consistently improves recognition performance across different tasks, input features, and noisy conditions when compared to a standard GRU.

2017-08-19

Interspeech 2017 (publié)

End-to-end optimization of goal-driven and visually grounded dialogue systems

Florian Strub

Harm de Vries

Jérémie Mary

Bilal Piot

Olivier Pietquin

End-to-end design of dialogue systems has recently become a popular research topic thanks to powerful tools such as encoder-decoder architec… (voir plus)tures for sequence-to-sequence learning. Yet, most current approaches cast human-machine dialogue management as a supervised learning problem, aiming at predicting the next utterance of a participant given the full history of the dialogue. This vision is too simplistic to render the intrinsic planning problem inherent to dialogue as well as its grounded nature , making the context of a dialogue larger than the sole history. This is why only chitchat and question answering tasks have been addressed so far using end-to-end architectures. In this paper, we introduce a Deep Reinforcement Learning method to optimize visually grounded task-oriented dialogues , based on the policy gradient algorithm. This approach is tested on a dataset of 120k dialogues collected through Mechanical Turk and provides encouraging results at solving both the problem of generating natural dialogues and the task of discovering a specific object in a complex picture.

2017-08-18

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence (publié)

Adversarial Generation of Natural Language

Sandeep Subramanian

Sai Rajeswar

Francis Dutil

Christopher Pal

Generative Adversarial Networks (GANs) have gathered a lot of attention from the computer vision community, yielding impressive results for … (voir plus)image generation. Advances in the adversarial generation of natural language from noise however are not commensurate with the progress made in generating images, and still lag far behind likelihood based methods. In this paper, we take a step towards generating natural language with a GAN objective alone. We introduce a simple baseline that addresses the discrete output space problem without relying on gradient estimators and show that it is able to achieve state-of-the-art results on a Chinese poem generation dataset. We present quantitative results on generating sentences from context-free and probabilistic context-free grammars, and qualitative language modeling results. A conditional version is also described that can generate sequences conditioned on sentence characteristics.

2017-07-31

Proceedings of the 2nd Workshop on Representation Learning for NLP (publié)

Approximate Value Iteration with Temporally Extended Actions (Extended Abstract)

Timothy A. Mann

Shie Mannor

Doina Precup

The options framework provides a concrete way to implement and reason about temporally extended actions. Existing literature has demonstrate… (voir plus)d the value of planning with options empirically, but there is a lack of theoretical analysis formalizing when planning with options is more efficient than planning with primitive actions. We provide a general analysis of the convergence rate of a popular Approximate Value Iteration (AVI) algorithm called Fitted Value Iteration (FVI) with options. Our analysis reveals that longer duration options and a pessimistic estimate of the value function both lead to faster convergence. Furthermore, options can improve convergence even when they are suboptimal and sparsely distributed throughout the state space. Next we consider generating useful options for planning based on a subset of landmark states. This suggests a new algorithm, Landmarkbased AVI (LAVI), that represents the value function only at landmark states. We analyze OFVI and LAVI using the proposed landmark-based options and compare the two algorithms. Our theoretical and experimental results demonstrate that options can play an important role in AVI by decreasing approximation error and inducing fast convergence.

2017-07-31

International Joint Conference on Artificial Intelligence (publié)

Plan, Attend, Generate: Character-Level Neural Machine Translation with Planning

Caglar Gulçehre

Francis Dutil

Adam Trischler

Yoshua Bengio

We investigate the integration of a planning mechanism into an encoder-decoder architecture with attention. We develop a model that can plan… (voir plus) ahead when it computes alignments between the source and target sequences not only for a single time-step but for the next k time-steps as well by constructing a matrix of proposed future alignments and a commitment vector that governs whether to follow or recompute the plan. This mechanism is inspired by strategic attentive reader and writer (STRAW) model, a recent neural architecture for planning with hierarchical reinforcement learning that can also learn higher level temporal abstractions. Our proposed model is end-to-end trainable with differentiable operations. We show that our model outperforms strong baselines on character-level translation task from WMT’15 with fewer parameters and computes alignments that are qualitatively intuitive.

2017-07-31

Proceedings of the 2nd Workshop on Representation Learning for NLP (publié)

Predicting Success in Goal-Driven Human-Human Dialogues

Michael Noseworthy

Jackie CK Cheung

Joelle Pineau

In goal-driven dialogue systems, success is often defined based on a structured definition of the goal. This requires that the dialogue syst… (voir plus)em be constrained to handle a specific class of goals and that there be a mechanism to measure success with respect to that goal. However, in many human-human dialogues the diversity of goals makes it infeasible to define success in such a way. To address this scenario, we consider the task of automatically predicting success in goal-driven human-human dialogues using only the information communicated between participants in the form of text. We build a dataset from stackoverflow.com which consists of exchanges between two users in the technical domain where ground-truth success labels are available. We then propose a turn-based hierarchical neural network model that can be used to predict success without requiring a structured goal definition. We show this model outperforms rule-based heuristics and other baselines as it is able to detect patterns over the course of a dialogue and capture notions such as gratitude.

2017-07-31

SIGDIAL Conference (publié)

Self-organized Hierarchical Softmax

Yikang Shen

Shawn Tan

Christopher Pal

We propose a new self-organizing hierarchical softmax formulation for neural-network-based language models over large vocabularies. Instead … (voir plus)of using a predefined hierarchical structure, our approach is capable of learning word clusters with clear syntactical and semantic meaning during the language model training process. We provide experiments on standard benchmarks for language modeling and sentence compression tasks. We find that this approach is as fast as other efficient softmax approximations, while achieving comparable or even better performance relative to similar full softmax models.

2017-07-25

ArXiv (prépublication)

A dataset and exploration of models for understanding video data through fill-in-the-blank question-answering

Tegan Maharaj

Nicolas Ballas

Anna Rohrbach

Christopher Pal

While deep convolutional neural networks frequently approach or exceed human-level performance at benchmark tasks involving static images, e… (voir plus)xtending this success to moving images is not straightforward. Having models which can learn to understand video is of interest for many applications, including content recommendation, prediction, summarization, event/object detection and understanding human visual perception, but many domains lack sufficient data to explore and perfect video models. In order to address the need for a simple, quantitative benchmark for developing and understanding video, we present MovieFIB, a fill-in-the-blank question-answering dataset with over 300,000 examples, based on descriptive video annotations for the visually impaired. In addition to presenting statistics and a description of the dataset, we perform a detailed analysis of 5 different models' predictions, and compare these with human performance. We investigate the relative importance of language, static (2D) visual features, and moving (3D) visual features; the effects of increasing dataset size, the number of frames sampled; and of vocabulary size. We illustrate that: this task is not solvable by a language model alone; our model combining 2D and 3D visual information indeed provides the best result; all models perform significantly worse than human-level. We provide human evaluations for responses given by different models and find that accuracy on the MovieFIB evaluation corresponds well with human judgement. We suggest avenues for improving video models, and hope that the proposed dataset can be useful for measuring and encouraging progress in this very interesting field.

2017-07-20

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (publié)

GuessWhat?! Visual Object Discovery through Multi-modal Dialogue

Harm de Vries

Florian Strub

A. Chandar

Olivier Pietquin

Hugo Larochelle

We introduce GuessWhat?!, a two-player guessing game as a testbed for research on the interplay of computer vision and dialogue systems. The… (voir plus) goal of the game is to locate an unknown object in a rich image scene by asking a sequence of questions. Higher-level image understanding, like spatial reasoning and language grounding, is required to solve the proposed task. Our key contribution is the collection of a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images. We explain our design decisions in collecting the dataset and introduce the oracle and questioner tasks that are associated with the two players of the game. We prototyped deep learning models to establish initial baselines of the introduced tasks.

2017-07-20

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (publié)

A Closer Look at Memorization in Deep Networks

Devansh Arpit

Stanisław Jastrzębski

David Krueger

Maxinder S. Kanwal

We examine the role of memorization in deep learning, drawing connections to capacity, generalization, and adversarial robustness. While dee… (voir plus)p networks are capable of memorizing noise data, our results suggest that they tend to prioritize learning simple patterns first. In our experiments, we expose qualitative differences in gradient-based optimization of deep neural networks (DNNs) on noise vs. real data. We also demonstrate that for appropriately tuned explicit regularization (e.g., dropout) we can degrade DNN training performance on noise datasets without compromising generalization on real data. Our analysis suggests that the notions of effective capacity which are dataset independent are unlikely to explain the generalization performance of deep networks when trained with gradient based methods because training data itself plays an important role in determining the degree of memorization.

2017-07-16

Proceedings of the 34th International Conference on Machine Learning (publié)